paper-with-me

APPO

Asynchronous Proximal Policy Optimization

2000년 도입 · 논문 4편에서 사용

출처: Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning

소개 논문: Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning

Distributed Reinforcement Learning · Reinforcement Learning